Instructions to use m-a-p/OProver-32B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use m-a-p/OProver-32B-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="m-a-p/OProver-32B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("m-a-p/OProver-32B-Base")
model = AutoModelForCausalLM.from_pretrained("m-a-p/OProver-32B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use m-a-p/OProver-32B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "m-a-p/OProver-32B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "m-a-p/OProver-32B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/m-a-p/OProver-32B-Base

SGLang

How to use m-a-p/OProver-32B-Base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "m-a-p/OProver-32B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "m-a-p/OProver-32B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "m-a-p/OProver-32B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "m-a-p/OProver-32B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use m-a-p/OProver-32B-Base with Docker Model Runner:
```
docker model run hf.co/m-a-p/OProver-32B-Base
```

dma2077 commited on 1 day ago

Commit

c2764b2

verified ·

1 Parent(s): 0e86031

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

.gitattributes +2 -0
assets/main_results.png +3 -0
assets/oproofs.png +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/main_results.png filter=lfs diff=lfs merge=lfs -text
+assets/oproofs.png filter=lfs diff=lfs merge=lfs -text

assets/main_results.png ADDED Viewed

Git LFS Details

SHA256: 1f8e703a29863a63eb8de24ba05da572775eba968ed11cdd72c6d1a1abc2f472
Pointer size: 131 Bytes
Size of remote file: 308 kB

assets/oproofs.png ADDED Viewed

Git LFS Details

SHA256: 648f24bd14a29890d8d55d557f62e0cf1aec623ce3f75ca8665b360667c0dad8
Pointer size: 131 Bytes
Size of remote file: 256 kB